@wix/evalforge-types 0.46.0 → 0.48.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/build/index.js +25 -13
- package/build/index.js.map +2 -2
- package/build/index.mjs +24 -12
- package/build/index.mjs.map +2 -2
- package/build/types/common/models.d.ts +1 -1
- package/build/types/evaluation/eval-run.d.ts +7 -1
- package/build/types/project/project.d.ts +3 -0
- package/build/types/scenario/test-scenario.d.ts +3 -0
- package/package.json +2 -2
package/build/index.mjs
CHANGED
|
@@ -929,17 +929,17 @@ var WebhookIdentityType;
|
|
|
929
929
|
})(WebhookIdentityType || (WebhookIdentityType = {}));
|
|
930
930
|
|
|
931
931
|
// src/common/models.ts
|
|
932
|
-
var
|
|
932
|
+
var AVAILABLE_CLAUDE_MODEL_IDS = Object.values(
|
|
933
933
|
ClaudeModel
|
|
934
934
|
).filter(
|
|
935
935
|
(v) => typeof v === "string" && v !== ClaudeModel.UNKNOWN_CLAUDE_MODEL
|
|
936
936
|
);
|
|
937
937
|
var PREFERRED_JUDGE_MODEL = "CLAUDE_4_5_HAIKU_1_0";
|
|
938
|
-
var DEFAULT_JUDGE_MODEL =
|
|
938
|
+
var DEFAULT_JUDGE_MODEL = AVAILABLE_CLAUDE_MODEL_IDS.includes(
|
|
939
939
|
PREFERRED_JUDGE_MODEL
|
|
940
|
-
) ? PREFERRED_JUDGE_MODEL :
|
|
940
|
+
) ? PREFERRED_JUDGE_MODEL : AVAILABLE_CLAUDE_MODEL_IDS[0];
|
|
941
941
|
var ClaudeModelSchema = z4.enum(
|
|
942
|
-
|
|
942
|
+
AVAILABLE_CLAUDE_MODEL_IDS
|
|
943
943
|
);
|
|
944
944
|
var AVAILABLE_OPENAI_MODEL_IDS = Object.values(
|
|
945
945
|
Model
|
|
@@ -950,7 +950,7 @@ var OpenAIModelSchema = z4.enum(
|
|
|
950
950
|
AVAILABLE_OPENAI_MODEL_IDS
|
|
951
951
|
);
|
|
952
952
|
var ALL_AVAILABLE_MODEL_IDS = [
|
|
953
|
-
...
|
|
953
|
+
...AVAILABLE_CLAUDE_MODEL_IDS,
|
|
954
954
|
...AVAILABLE_OPENAI_MODEL_IDS
|
|
955
955
|
];
|
|
956
956
|
var AnyModelSchema = z4.enum(
|
|
@@ -1601,7 +1601,9 @@ var TestScenarioSchema = TenantEntitySchema.extend({
|
|
|
1601
1601
|
/** IDs of saved assertions to evaluate (from assertions table) - legacy, use assertionLinks */
|
|
1602
1602
|
assertionIds: z24.array(z24.string()).optional(),
|
|
1603
1603
|
/** Linked assertions with per-scenario parameter values */
|
|
1604
|
-
assertionLinks: z24.array(ScenarioAssertionLinkSchema).optional()
|
|
1604
|
+
assertionLinks: z24.array(ScenarioAssertionLinkSchema).optional(),
|
|
1605
|
+
/** Tags for categorisation and filtering */
|
|
1606
|
+
tags: z24.array(z24.string()).optional()
|
|
1605
1607
|
});
|
|
1606
1608
|
var CreateTestScenarioInputSchema = TestScenarioSchema.omit({
|
|
1607
1609
|
id: true,
|
|
@@ -1870,7 +1872,7 @@ var EvalRunSchema = TenantEntitySchema.extend({
|
|
|
1870
1872
|
skillsGroupId: z28.string().optional(),
|
|
1871
1873
|
/** Map of skillId to skillVersionId for this run */
|
|
1872
1874
|
skillVersions: z28.record(z28.string(), z28.string()).optional(),
|
|
1873
|
-
/** Scenario IDs to run */
|
|
1875
|
+
/** Scenario IDs to run (always present — resolved server-side from tags when needed) */
|
|
1874
1876
|
scenarioIds: z28.array(z28.string()),
|
|
1875
1877
|
/** Current status */
|
|
1876
1878
|
status: EvalStatusSchema,
|
|
@@ -1905,7 +1907,9 @@ var EvalRunSchema = TenantEntitySchema.extend({
|
|
|
1905
1907
|
/** Sub-agent IDs to enable for this run (optional) */
|
|
1906
1908
|
subAgentIds: z28.array(z28.string()).optional(),
|
|
1907
1909
|
/** Rule IDs to enable for this run (optional) */
|
|
1908
|
-
ruleIds: z28.array(z28.string()).optional()
|
|
1910
|
+
ruleIds: z28.array(z28.string()).optional(),
|
|
1911
|
+
/** Tags used to select scenarios for this run (for traceability) */
|
|
1912
|
+
tags: z28.array(z28.string()).optional()
|
|
1909
1913
|
});
|
|
1910
1914
|
var CreateEvalRunInputSchema = EvalRunSchema.omit({
|
|
1911
1915
|
id: true,
|
|
@@ -1916,8 +1920,15 @@ var CreateEvalRunInputSchema = EvalRunSchema.omit({
|
|
|
1916
1920
|
results: true,
|
|
1917
1921
|
aggregateMetrics: true,
|
|
1918
1922
|
startedAt: true,
|
|
1919
|
-
completedAt: true
|
|
1920
|
-
|
|
1923
|
+
completedAt: true,
|
|
1924
|
+
scenarioIds: true
|
|
1925
|
+
}).extend({
|
|
1926
|
+
/** Optional on input — backend resolves from tags when not provided */
|
|
1927
|
+
scenarioIds: z28.array(z28.string()).optional()
|
|
1928
|
+
}).refine(
|
|
1929
|
+
(data) => data.scenarioIds && data.scenarioIds.length > 0 || data.tags && data.tags.length > 0,
|
|
1930
|
+
{ message: "Either scenarioIds or tags must be provided" }
|
|
1931
|
+
);
|
|
1921
1932
|
var EvaluationProgressSchema = z28.object({
|
|
1922
1933
|
runId: z28.string(),
|
|
1923
1934
|
targetId: z28.string(),
|
|
@@ -2091,7 +2102,8 @@ var ProjectSchema = BaseEntitySchema.extend({
|
|
|
2091
2102
|
appId: z31.string().optional().describe("The ID of the app in Dev Center"),
|
|
2092
2103
|
appSecret: z31.string().optional().describe("The secret of the app in Dev Center"),
|
|
2093
2104
|
useWixAuth: z31.boolean().optional().describe("Enable Wix CLI/MCP auth for evaluations"),
|
|
2094
|
-
useBase44Auth: z31.boolean().optional().describe("Enable Base44 auth for evaluations")
|
|
2105
|
+
useBase44Auth: z31.boolean().optional().describe("Enable Base44 auth for evaluations"),
|
|
2106
|
+
scenarioTags: z31.array(z31.string()).optional().describe("Project-level tag vocabulary for scenarios")
|
|
2095
2107
|
});
|
|
2096
2108
|
var CreateProjectInputSchema = ProjectSchema.omit({
|
|
2097
2109
|
id: true,
|
|
@@ -2265,7 +2277,7 @@ function getSystemAssertion(id) {
|
|
|
2265
2277
|
export {
|
|
2266
2278
|
AGENT_TYPE_LABELS,
|
|
2267
2279
|
ALL_AVAILABLE_MODEL_IDS,
|
|
2268
|
-
|
|
2280
|
+
AVAILABLE_CLAUDE_MODEL_IDS,
|
|
2269
2281
|
AVAILABLE_OPENAI_MODEL_IDS,
|
|
2270
2282
|
AVAILABLE_RUN_COMMANDS,
|
|
2271
2283
|
AVAILABLE_TOOL_NAMES,
|